DEEP LEARNING-BASED BRAIN TUMOR CLASSIFICATION MODEL USING CONVOLUTIONAL NEURAL NETWORK AND DATA AUGMENTATION TECHNIQUES

Abstract

Brain tumors are among the most aggressive and fatal forms of cancer; therefore, early and accurate detection is essential for improving treatment outcomes. This study presents a brain tumor classification model that leverages deep learning techniques to facilitate the automatic identification of tumor types. The model employs convolutional neural networks (CNNs) to analyze magnetic resonance imaging (MRI) scans and classify brain tumor images into specific categories. CNNs have proven to be highly effective in feature extraction and image classification, making them a reliable approach for processing medical imaging data and enhancing diagnostic precision. The dataset used in this study consists of publicly available MRI images that have undergone preprocessing to ensure uniformity and improved quality. The model is trained using supervised learning, in which labeled images are used to help the network recognize patterns associated with different tumor types. Data augmentation techniques are also applied to improve generalization and mitigate over fitting. The model’s performance is evaluated using metrics such as accuracy, precision, recall, and F1-score, showing significant improvement over traditional ML methods. Deep learning-based models offer a powerful tool for enhancing the accuracy and efficiency of brain tumor diagnosis, providing valuable support to clinicians in medical practice. Future research will focus on expanding the dataset and exploring advanced model architectures to optimize performance and reliability